© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 4257
    Prev
    Next
    INDEX
    Explanations

    animal or pet owner relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĶĢ
    -0.09
    åľ¨æĪijçľĭæĿ¥
    -0.09
    itzer
    -0.09
    head
    -0.08
    åıĽ
    -0.08
    æµ·çĽĹ
    -0.08
    åĪ¨
    -0.08
    è°Ĺ
    -0.08
    Sibling
    -0.08
    ITCH
    -0.08
    POSITIVE LOGITS
    驯
    0.15
    åĬ¨çī©
    0.14
    饲åħ»
    0.13
     animal
    0.12
    饲
    0.11
    è±¢
    0.11
    åħ»
    0.11
    çī©ç§į
    0.11
    å°ıå¾®
    0.10
    驾é©Ń
    0.10
    Activations Density 0.091%

    No Known Activations